Bartosz Cywinski

12 papers A* 2A 1Journal 9
YearRankTypeTitle / Venue / Authors
2026 J jnl
Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation.
CoRR
Helena Casademunt, Bartosz Cywinski, Khoi Tran, Arya Jakkli, Samuel Marks, Neel Nanda
2026 J jnl
Simple LLM Baselines are Competitive for Model Diffing.
CoRR
Elias Kempf, Simon Schrodi, Bartosz Cywinski, Thomas Brox, Neel Nanda, Arthur Conmy
2025 J jnl
Adapt & Align: Continual Learning with Generative Models' Latent Space Alignment.
Neurocomputing
Kamil Deja, Bartosz Cywinski, Jan Rybarczyk, Tomasz Trzcinski
2025 J jnl
Eliciting Secret Knowledge from Language Models.
CoRR
Bartosz Cywinski, Emil Ryd, Rowan Wang, Senthooran Rajamanoharan, Neel Nanda, Arthur Conmy, Samuel Marks
2025 A conf
GUIDE: Guidance-Based Incremental Learning with Diffusion Models.
ECAI
Bartosz Cywinski, Kamil Deja, Tomasz Trzcinski, Bartlomiej Twardowski, Lukasz Kucinski
2025 A* conf
Precise Parameter Localization for Textual Generation in Diffusion Models.
ICLR
Lukasz Staniszewski, Bartosz Cywinski, Franziska Boenisch, Kamil Deja, Adam Dziedzic
2025 J jnl
Precise Parameter Localization for Textual Generation in Diffusion Models.
CoRR
Lukasz Staniszewski, Bartosz Cywinski, Franziska Boenisch, Kamil Deja, Adam Dziedzic
2025 A* conf
SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders.
ICML
Bartosz Cywinski, Kamil Deja
2025 J jnl
SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders.
CoRR
Bartosz Cywinski, Kamil Deja
2025 J jnl
Towards eliciting latent knowledge from LLMs with mechanistic interpretability.
CoRR
Bartosz Cywinski, Emil Ryd, Senthooran Rajamanoharan, Neel Nanda
2024 J jnl
GUIDE: Guidance-based Incremental Learning with Diffusion Models.
CoRR
Bartosz Cywinski, Kamil Deja, Tomasz Trzcinski, Bartlomiej Twardowski, Lukasz Kucinski
2023 J jnl
Adapt & Align: Continual Learning with Generative Models Latent Space Alignment.
CoRR
Kamil Deja, Bartosz Cywinski, Jan Rybarczyk, Tomasz Trzcinski